Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 25085
    Prev
    Next
    INDEX
    Explanations

    the concept of fatigue and its variations in context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.81
     الرياضيه
    -0.68
    /**
    -0.63
     stanovnika
    -0.62
    mber
    -0.59
    edip
    -0.59
     solches
    -0.59
    dam
    -0.59
    ship
    -0.59
    nologue
    -0.58
    POSITIVE LOGITS
     Fatigue
    1.18
     fatigue
    1.12
    fatigue
    1.05
    Fatigue
    1.03
    phosa
    0.80
     CreateTagHelper
    0.77
    enderror
    0.76
    mybatisplus
    0.76
     fatigued
    0.73
     fatig
    0.71
    Activations Density 0.002%

    No Known Activations